Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts
Bo Wang, Heyan Huang, Yaolin Li +5
Retrieval-augmented generation (RAG) improves language models by grounding generation in external context. However, it can be fragile when the retrieved context conflicts with the…
cs.CL2026
Pardon? Evaluating Conversational Repair in Large Audio-Language Models
Shuanghong Huang, Jinlei Xu, Youchao Zhou +4
Large Audio-Language Models (LALMs) have demonstrated strong performance in spoken question answering (QA), with existing evaluations primarily focusing on answer accuracy and robu…
cs.CL2025
Training-free Truthfulness Detection via Sparse MLP Value Vectors
Runheng Liu, Heyan Huang, Xingchen Xiao +2
Large language models (LLMs) are prone to generating factually incorrect content, motivating methods for assessing truthfulness from internal model signals. While supervised probin…